Cross-Domain Variational Autoencoder for Recommender Systems

Shi, Jianyong; Wang, Quanmin

doi:10.1109/icait.2019.8935901

Cited by 8 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The YOLO family of algorithms is a typical class of onestage target detection algorithms released in 2015, and YOLOv7 is a more advanced version of the family with excellent speed and accuracy in the range of 5 FPS to 160 FPS [24]. In real-time image and video analysis, etc., YOLOv7 is able to quickly and accurately detect multiple objects and provide their position and category information, so in this paper, we choose the YOLOv7 model for stud detection [25]. The YOLOv7 network is mainly composed of the following parts, and the network structure of YOLOv7 is shown in Fig.…”

Section: Related Workmentioning

confidence: 99%

Efficient Object Detection and Recognition of Body Welding Studs Based on Improved YOLOv7

Huang,

Peng,

et al. 2024

IEEE Access

View full text Add to dashboard Cite

The welding stud is a widely used part in automobile manufacturing, and its welding quality plays a crucial role in component assembly efficiency and vehicle quality. In welded stud target inspection, the complex body environment and different lighting conditions will have a certain impact on the inspection accuracy, and most of the existing methods have limited efficiency. In this paper, in order to solve the problems of low accuracy and slow speed in the stud target inspection process, we propose an innovative welding stud target inspection method based on YOLOv7. First, the EfficientFormerV2 backbone network is adopted to utilize the new partial convolution, which can extract spatial features more efficiently, reduce redundant computation, and improve the detection speed. Secondly, the bounding box loss function is changed to NWD, which reduces the loss value, accelerates the convergence speed of the network model, and better improves the detection of studs. After the test, the improved YOLOv7 network model is better than the traditional network in both speed and accuracy of welded stud target detection. (1) The mAP0.5 increased from 94.6% to 95.2%, and the mAP0.5:0.95 increased from 63.7% to 65.4%. (2) The detection speed increased from 96.1 f/s to 147.1 f/s. The results of the study can provide technical support for the subsequent tasks of automatic detection and position estimation of body welding studs.

show abstract

Section: Related Workmentioning

confidence: 99%

Efficient Object Detection and Recognition of Body Welding Studs Based on Improved YOLOv7

Huang,

Peng,

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Recent TMCDR [7] and PTUPCDR [39] follow the MAML [62] framework to learn a meta network to substitute the mapping function for the better recommendation, which can still be regarded as a particular form of the embedding-and-mapping paradigm. Besides, motivated by the success of VAE [25] framework in collaborative filtering, CDVAE [9], AlignVAE [63] and SA-VAE [8] are proposed based on Bayesian-VAE to learn the mapping function. Compared with these aforementioned methods, our CDRIB has important design differences as follows:…”

Section: ) Cross-domain Recommendation To Overlapping Usersmentioning

confidence: 99%

“…Despite their success, most EMCDR-based approaches [5,6,7,8,9] pre-train user/item representations independently which could be easily biased on each domain, limiting the transferring effectiveness of the mapping function. As shown in Fig.…”

Section: Introductionmentioning

confidence: 99%

Cross-Domain Recommendation to Cold-Start Users via Variational Information Bottleneck

Cao¹,

Sheng²,

Xu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Recommender systems have been widely deployed in many real-world applications, but usually suffer from the longstanding user cold-start problem. As a promising way, Cross-Domain Recommendation (CDR) has attracted a surge of interest, which aims to transfer the user preferences observed in the source domain to make recommendations in the target domain. Previous CDR approaches mostly achieve the goal by following the Embedding and Mapping (EMCDR) idea which attempts to learn a mapping function to transfer the pre-trained user representations (embeddings) from the source domain into the target domain. However, they pre-train the user/item representations independently for each domain, ignoring to consider both domain interactions simultaneously. Therefore, the biased pre-trained representations inevitably involve the domain-specific information which may lead to negative impact to transfer information across domains. In this work, we consider a key point of the CDR task: what information needs to be shared across domains? To achieve the above idea, this paper utilizes the information bottleneck (IB) principle, and proposes a novel approach termed as CDRIB to enforce the representations encoding the domainshared information. To derive the unbiased representations, we devise two IB regularizers to model the cross-domain/in-domain user-item interactions simultaneously and thereby CDRIB could consider both domain interactions jointly for de-biasing. With an additional contrastive information regularizer, CDRIB can also capture cross-domain user-user correlations. In this way, those regularizers encourage the representations to encode the domain-shared information, which has the capability to make recommendations in both domains directly. To the best of our knowledge, this paper is the first work to capture the domain-shared information for cold-start users via variational information bottleneck. Empirical experiments illustrate that CDRIB outperforms the state-of-the-art approaches on four realworld cross-domain datasets, demonstrating the effectiveness of adopting the information bottleneck for CDR.

show abstract

“…A common idea of CDR methods is to train the model with the overlapping users appearing in both the source and target domain, and then make recommendation for the cold-start users that only have interactions in the source domain. To achieve the above idea, traditional CDR methods [10,20,27,30,39] follow the Embedding and Mapping (EMCDR) paradigm (as shown in Fig. 1(a)).…”

Section: Introductionmentioning

confidence: 99%

CDRNP: Cross-Domain Recommendation to Cold-Start Users via Neural Process

Li,

Sheng,

Cao

et al. 2024

Proceedings of the 17th ACM International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

Cross-domain recommendation (CDR) has been proven as a promising way to tackle the user cold-start problem, which aims to make recommendations for users in the target domain by transferring the user preference derived from the source domain. Traditional CDR studies follow the embedding and mapping (EMCDR) paradigm, which transfers user representations from the source to target domain by learning a user-shared mapping function, neglecting the user-specific preference. Recent CDR studies attempt to learn user-specific mapping functions in meta-learning paradigm, which regards each user's CDR as an individual task, but neglects the preference correlations among users, limiting the beneficial information for user representations. Moreover, both of the paradigms neglect the explicit user-item interactions from both domains during the mapping process. To address the above issues, this paper proposes a novel CDR framework with neural process (NP), termed as CDRNP. Particularly, it develops the meta-learning paradigm to leverage user-specific preference, and further introduces a stochastic process by NP to capture the preference correlations among the overlapping and cold-start users, thus generating more powerful mapping functions by mapping the user-specific preference and common preference correlations to a predictive probability distribution. In addition, we also introduce a preference remainer to enhance the common preference from the overlapping users, and finally devises an adaptive conditional decoder with preference modulation to make prediction for cold-start users with items in the target domain. Experimental results demonstrate that CDRNP outperforms previous SOTA methods in three real-world CDR scenarios.

show abstract

Cross-Domain Variational Autoencoder for Recommender Systems

Cited by 8 publications

References 8 publications

Efficient Object Detection and Recognition of Body Welding Studs Based on Improved YOLOv7

Efficient Object Detection and Recognition of Body Welding Studs Based on Improved YOLOv7

Cross-Domain Recommendation to Cold-Start Users via Variational Information Bottleneck

CDRNP: Cross-Domain Recommendation to Cold-Start Users via Neural Process

Contact Info

Product

Resources

About